Cross-Domain Offshore Wind Power Forecasting: Transfer Learning Through Meteorological Clusters

TL;DR

This work tackles the data scarcity challenge of offshore wind power forecasting at new sites by introducing a climate-aware transfer-learning framework. It learns domain-agnostic weather representations from a large European dataset, clusters periods into weather-patterned regimes, and trains cluster-specific Gaussian Processes to forecast one-hour-ahead power. Target sites are mapped to these weather clusters and fine-tuned using limited site data, enabling rapid, accurate forecasts with under roughly five months of local measurements; the approach achieves an average MAE of about $3.52\%$ with $20\%$ data, outperforming baselines that require more data. The method holds practical potential for accelerating offshore wind development, reducing upfront data collection costs, and enabling early-stage wind resource assessment, while opening avenues for geographic transfer and wake-effect integration.

Abstract

Ambitious decarbonisation targets are catalysing growth in orders of new offshore wind farms. For these newly commissioned plants to run, accurate power forecasts are needed from the onset. These allow grid stability, good reserve management and efficient energy trading. Despite machine learning models having strong performances, they tend to require large volumes of site-specific data that new farms do not yet have. To overcome this data scarcity, we propose a novel transfer learning framework that clusters power output according to covariate meteorological features. Rather than training a single, general-purpose model, we thus forecast with an ensemble of expert models, each trained on a cluster. As these pre-trained models each specialise in a distinct weather pattern, they adapt efficiently to new sites and capture transferable, climate-dependent dynamics. Through the expert models' built-in calibration to seasonal and meteorological variability, we remove the industry-standard requirement of local measurements over a year. Our contributions are two-fold - we propose this novel framework and comprehensively evaluate it on eight offshore wind farms, achieving accurate cross-domain forecasting with under five months of site-specific data. Our experiments achieve a MAE of 3.52\%, providing empirical verification that reliable forecasts do not require a full annual cycle. Beyond power forecasting, this climate-aware transfer learning method opens new opportunities for offshore wind applications such as early-stage wind resource assessment, where reducing data requirements can significantly accelerate project development whilst effectively mitigating its inherent risks.

Figures (5)

• Figure 1: Methodology overview.
• Figure 2: Location and cluster assignment for available wind farms with the selected source wind farms
• Figure 3: Latent space manifold visualised via t-SNE, showing the distribution of training periods across weather clusters.
• Figure 4: Mean wind speed distribution of training periods by cluster (exemplified by seed 84).
• Figure 5: Performance of GP forecasts, disaggregated by wind farm and cluster.